Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+pivotai_curriculum.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,95 @@
+---
+language:
+  - en
+tags:
+  - travel
+  - india
+  - curriculum-learning
+  - llama
+  - qlora
+  - itinerary-optimization
+  - grounding
+license: apache-2.0
+base_model: unsloth/Meta-Llama-3.1-8B
+datasets:
+  - ishreyadev/pivotai-synthetic-v2
+  - ishreyadev/pivotai-agent-traces
+metrics:
+  - bertscore
+model-index:
+  - name: pivotai-curriculum
+    results:
+      - task:
+          type: text-generation
+          name: Travel Itinerary Optimization
+        metrics:
+          - type: grounding_accuracy
+            value: 0.88
+            name: Grounding Accuracy
+          - type: bertscore_f1
+            value: 0.734
+            name: BERTScore F1
+          - type: red_team_pass
+            value: 0.60
+            name: Red-Team Robustness
+---
+
+# pivotai-curriculum
+
+Curriculum-trained Llama 3.1 8B for Indian domestic travel optimization. Uses **two-stage sequential training**: first on 4,749 Phase 1 synthetic pairs (domain knowledge), then on 449 Phase 2 agent reasoning traces (complex reasoning patterns).
+
+Part of the [pivotai](https://github.com/ishreya-dev/PivotAI) project. The curriculum hypothesis was that domain knowledge should precede complex reasoning patterns — similar to how students learn fundamentals before advanced topics. Results revealed an interesting trade-off: the model achieved the **highest grounding accuracy (88%)** and **best red-team robustness (60%)** of the three variants, but the Phase 2 training stage catastrophically disrupted structured JSON output (10.9% validity).
+
+## Model Details
+
+| Property | Value |
+|----------|-------|
+| Base model | `unsloth/Meta-Llama-3.1-8B` |
+| Training method | QLoRA r=8, α=16, dropout=0.05 (2-stage) |
+| Stage 1 data | 4,749 pairs (Phase 1 synthetic) — 424 steps |
+| Stage 2 data | 449 pairs (Phase 2 agent traces) — 171 steps |
+| Final train loss | 0.313 (Stage 2) |
+| Hardware | Lightning.ai A100 (bf16, seq_len=16384) |
+| Format | GGUF Q4_K_M (4.6 GB) |
+
+## Evaluation Results (92 test cases)
+
+| Metric | Score | Target | ✓/✗ |
+|--------|:-----:|:------:|:---:|
+| JSON valid | **10.9%** | 85% | ✗ |
+| Savings found | — | 70% | — |
+| Schema compliance | 0.0% | 80% | ✗ |
+| BERTScore F1 | 0.734 | 0.70 | ✓ |
+| Intent alignment | 0.418 | 0.55 | ✗ |
+| Grounding accuracy | **0.880** | 0.60 | ✓ |
+| Reasoning coherence | 0.470 | 0.65 | ✗ |
+| Red-team pass | **60.0%** | 80% | ✗ |
+
+**Notable:** Despite near-zero JSON validity, grounding accuracy (0.88) nearly matches pivotai-ft (0.895). The model has absorbed real-world knowledge about Indian cities and travel patterns — it simply cannot format the output as valid JSON after Phase 2 training overwrote structured-output behavior.
+
+**Recommendation:** Use with JSON-constrained decoding (llama.cpp `--grammar`, Outlines, or similar) to recover structured output. The underlying knowledge is strong.
+
+## Usage with Ollama
+
+```bash
+ollama create pivotai-curriculum -f Modelfile.curriculum
+ollama run pivotai-curriculum
+```
+
+**Note:** Due to low JSON validity in standard inference, consider using grammar-constrained decoding for reliable structured output.
+
+## Limitations
+
+- JSON validity is 10.9% — standard inference rarely produces valid JSON. Use grammar-constrained decoding.
+- The Phase 2 curriculum stage appears to have overwritten Phase 1 structured-output training — a known curriculum learning failure mode.
+- Despite strong semantic knowledge, the model cannot be used without output post-processing.
+
+## Citation
+
+If you use this model, please cite:
+
+```
+Patnaik, A. V. S. (2026). Cost-Matched Data Generation for LLM Fine-Tuning: Comparing
+Supervised Fine-Tuning, Knowledge Distillation, and Curriculum Learning for an Agentic
+Travel-Planning System. Zenodo. https://doi.org/10.5281/zenodo.21198884
+```

gitattributes

@@ -0,0 +1,38 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+pivotai_curriculum.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+WHITEPAPER.pdf filter=lfs diff=lfs merge=lfs -text
+whitepaper.pdf filter=lfs diff=lfs merge=lfs -text

pivotai_curriculum.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9041223c9dff9a610231482924653a95256a81b178b5412e46eb1017b93a4cba
+size 4920734368